© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118812
    Prev
    Next
    INDEX
    Explanations

    law and report

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fly
    -0.79
    vario
    -0.75
     Works
    -0.74
    Rest
    -0.71
    すべき
    -0.69
     Schlafzimmer
    -0.69
     resting
    -0.69
     devotees
    -0.69
     begleiten
    -0.68
     erklären
    -0.68
    POSITIVE LOGITS
     orientations
    0.88
     Orientation
    0.85
     orientation
    0.83
    лябин
    0.82
     Democrá
    0.82
    rably
    0.81
    ánica
    0.77
     law
    0.75
    Orientation
    0.74
     Bhi
    0.73
    Activations Density 0.016%

    No Known Activations